Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4322 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1905. Min Range: -7.1905
Max Act: 7.1905. Min Act: -0.1700
Data Index: 100353 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1905. Min Range: -7.1905
Max Act: 7.1280. Min Act: -0.1700
Data Index: 2085350 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1905. Min Range: -7.1905
Max Act: 7.0655. Min Act: -0.1700
Data Index: 364141 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1905. Min Range: -7.1905
Max Act: 7.0030. Min Act: -0.1700
Data Index: 3685659 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1905. Min Range: -7.1905
Max Act: 7.0343. Min Act: -0.1700
Data Index: 8364060 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1905. Min Range: -7.1905
Max Act: 6.9405. Min Act: -0.1700
Data Index: 4036653 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1905. Min Range: -7.1905
Max Act: 6.9093. Min Act: -0.1700
Data Index: 7863400 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1905. Min Range: -7.1905
Max Act: 6.9093. Min Act: -0.1700
Data Index: 3342171 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1905. Min Range: -7.1905
Max Act: 6.8780. Min Act: -0.1700
Data Index: 6036450 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1905. Min Range: -7.1905
Max Act: 6.8780. Min Act: -0.1700
Data Index: 5653066 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1905. Min Range: -7.1905
Max Act: 6.8780. Min Act: -0.1700
Data Index: 6883702 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1905. Min Range: -7.1905
Max Act: 6.8468. Min Act: -0.1700
Data Index: 7744155 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1905. Min Range: -7.1905
Max Act: 6.8155. Min Act: -0.1700
Data Index: 2755933 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1905. Min Range: -7.1905
Max Act: 6.8468. Min Act: -0.1700
Data Index: 357058 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1905. Min Range: -7.1905
Max Act: 6.8155. Min Act: -0.1700
Data Index: 5423209 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1905. Min Range: -7.1905
Max Act: 6.8155. Min Act: -0.1700
Data Index: 176105 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1905. Min Range: -7.1905
Max Act: 6.7843. Min Act: -0.1700
Data Index: 6453665 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1905. Min Range: -7.1905
Max Act: 6.7843. Min Act: -0.1700
Data Index: 8575310 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1905. Min Range: -7.1905
Max Act: 6.7843. Min Act: -0.1700
Data Index: 8542996 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1905. Min Range: -7.1905
Max Act: 6.7530. Min Act: -0.1700
Data Index: 6925534 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19